End of training

README.md

@@ -0,0 +1,93 @@
+---
+license: mit
+base_model: thenlper/gte-small
+tags:
+- generated_from_trainer
+datasets:
+- nyt_ingredients
+model-index:
+- name: nyt-ingredient-tagger-gte-small
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# nyt-ingredient-tagger-gte-small
+
+This model is a fine-tuned version of [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) on the nyt_ingredients dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8647
+- Comment: {'precision': 0.700344295381693, 'recall': 0.8211302895322939, 'f1': 0.7559428461587748, 'number': 7184}
+- Name: {'precision': 0.8125, 'recall': 0.8314522197140707, 'f1': 0.8218668650055783, 'number': 9303}
+- Qty: {'precision': 0.987037037037037, 'recall': 0.9920233980324382, 'f1': 0.9895239358175308, 'number': 7522}
+- Range End: {'precision': 0.7394366197183099, 'recall': 0.9375, 'f1': 0.8267716535433071, 'number': 112}
+- Unit: {'precision': 0.9283142901862577, 'recall': 0.9870194707938093, 'f1': 0.9567672205194386, 'number': 6009}
+- Overall Precision: 0.8470
+- Overall Recall: 0.9005
+- Overall F1: 0.8729
+- Overall Accuracy: 0.8468
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- label_smoothing_factor: 0.1
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Comment                                                                                                   | Name                                                                                                      | Qty                                                                                                       | Range End                                                                                               | Unit                                                                                                      | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.9427        | 0.2   | 1000  | 0.9321          | {'precision': 0.6076682497393722, 'recall': 0.7789161098737936, 'f1': 0.6827173347214992, 'number': 6735} | {'precision': 0.7829228243021347, 'recall': 0.8126349278491081, 'f1': 0.7975022301516503, 'number': 8801} | {'precision': 0.97529493407356, 'recall': 0.9913939051918735, 'f1': 0.9832785279507451, 'number': 7088}   | {'precision': 0.52046783625731, 'recall': 0.978021978021978, 'f1': 0.6793893129770994, 'number': 91}    | {'precision': 0.914435009797518, 'recall': 0.982973494821836, 'f1': 0.9474663734032653, 'number': 5697}   | 0.8032            | 0.8839         | 0.8416     | 0.8183           |
+| 0.9169        | 0.4   | 2000  | 0.9112          | {'precision': 0.6358395387941388, 'recall': 0.7860430586488493, 'f1': 0.7030077684084721, 'number': 6735} | {'precision': 0.781960613643782, 'recall': 0.8166117486649245, 'f1': 0.798910626945309, 'number': 8801}   | {'precision': 0.9746502285635129, 'recall': 0.9926636568848759, 'f1': 0.9835744740336898, 'number': 7088} | {'precision': 0.6277372262773723, 'recall': 0.945054945054945, 'f1': 0.7543859649122806, 'number': 91}  | {'precision': 0.9176201372997712, 'recall': 0.9854309285588907, 'f1': 0.9503173931443081, 'number': 5697} | 0.8137            | 0.8875         | 0.8490     | 0.8256           |
+| 0.9           | 0.59  | 3000  | 0.9021          | {'precision': 0.6538183570224042, 'recall': 0.8059391239792131, 'f1': 0.7219525171244263, 'number': 6735} | {'precision': 0.7920824651825858, 'recall': 0.8207021929326213, 'f1': 0.8061383928571427, 'number': 8801} | {'precision': 0.9837443946188341, 'recall': 0.9904063205417607, 'f1': 0.9870641169853768, 'number': 7088} | {'precision': 0.6792452830188679, 'recall': 0.7912087912087912, 'f1': 0.7309644670050762, 'number': 91} | {'precision': 0.9138857235878235, 'recall': 0.9854309285588907, 'f1': 0.9483108108108108, 'number': 5697} | 0.8231            | 0.8925         | 0.8564     | 0.8302           |
+| 0.9061        | 0.79  | 4000  | 0.8912          | {'precision': 0.6613263785394933, 'recall': 0.7906458797327395, 'f1': 0.7202272266179753, 'number': 6735} | {'precision': 0.7952695269526953, 'recall': 0.821383933643904, 'f1': 0.8081158124196521, 'number': 8801}  | {'precision': 0.985236220472441, 'recall': 0.9885722347629797, 'f1': 0.9869014084507043, 'number': 7088}  | {'precision': 0.656, 'recall': 0.9010989010989011, 'f1': 0.7592592592592593, 'number': 91}              | {'precision': 0.9215106732348112, 'recall': 0.9850798665964543, 'f1': 0.9522355137015356, 'number': 5697} | 0.8289            | 0.8889         | 0.8578     | 0.8326           |
+| 0.8889        | 0.99  | 5000  | 0.8908          | {'precision': 0.6653019447287615, 'recall': 0.7720861172976986, 'f1': 0.7147275101367603, 'number': 6735} | {'precision': 0.7959925134867335, 'recall': 0.8214975570957845, 'f1': 0.8085439498993513, 'number': 8801} | {'precision': 0.9857926571951048, 'recall': 0.9887133182844243, 'f1': 0.9872508276396421, 'number': 7088} | {'precision': 0.6439393939393939, 'recall': 0.9340659340659341, 'f1': 0.7623318385650225, 'number': 91} | {'precision': 0.9227729293594599, 'recall': 0.9836756187467088, 'f1': 0.9522514868309261, 'number': 5697} | 0.8317            | 0.8844         | 0.8572     | 0.8311           |
+| 0.88          | 1.19  | 6000  | 0.8873          | {'precision': 0.660211910851297, 'recall': 0.8048997772828508, 'f1': 0.7254114813327982, 'number': 6735}  | {'precision': 0.7929331723910896, 'recall': 0.8210430632882627, 'f1': 0.8067433292397008, 'number': 8801} | {'precision': 0.9827899818105499, 'recall': 0.9909706546275395, 'f1': 0.9868633649455567, 'number': 7088} | {'precision': 0.635036496350365, 'recall': 0.9560439560439561, 'f1': 0.7631578947368421, 'number': 91}  | {'precision': 0.9224067072168338, 'recall': 0.984904335615236, 'f1': 0.9526315789473684, 'number': 5697}  | 0.8266            | 0.8929         | 0.8585     | 0.8338           |
+| 0.8751        | 1.39  | 7000  | 0.8866          | {'precision': 0.6715582638975252, 'recall': 0.8017817371937639, 'f1': 0.7309149972929073, 'number': 6735} | {'precision': 0.8020833333333334, 'recall': 0.8224065447108283, 'f1': 0.8121178120617111, 'number': 8801} | {'precision': 0.9849719101123595, 'recall': 0.9894187358916479, 'f1': 0.9871903153153153, 'number': 7088} | {'precision': 0.6258992805755396, 'recall': 0.9560439560439561, 'f1': 0.7565217391304349, 'number': 91} | {'precision': 0.9254720105995363, 'recall': 0.9808671230472178, 'f1': 0.9523647209203238, 'number': 5697} | 0.8341            | 0.8914         | 0.8618     | 0.8348           |
+| 0.8816        | 1.58  | 8000  | 0.8823          | {'precision': 0.6672340425531915, 'recall': 0.8148478099480326, 'f1': 0.7336898395721925, 'number': 6735} | {'precision': 0.797549398388343, 'recall': 0.8209294398363822, 'f1': 0.8090705487122061, 'number': 8801}  | {'precision': 0.9851018973998594, 'recall': 0.988854401805869, 'f1': 0.9869745828346124, 'number': 7088}  | {'precision': 0.6439393939393939, 'recall': 0.9340659340659341, 'f1': 0.7623318385650225, 'number': 91} | {'precision': 0.9253386190948133, 'recall': 0.9833245567842724, 'f1': 0.9534507701472215, 'number': 5697} | 0.8308            | 0.8943         | 0.8614     | 0.8360           |
+| 0.8756        | 1.78  | 9000  | 0.8817          | {'precision': 0.6767485822306238, 'recall': 0.7973273942093542, 'f1': 0.7321063394683027, 'number': 6735} | {'precision': 0.8019714254070218, 'recall': 0.8227474150664698, 'f1': 0.8122265844083006, 'number': 8801} | {'precision': 0.9834641255605381, 'recall': 0.9901241534988713, 'f1': 0.9867829021372329, 'number': 7088} | {'precision': 0.7043478260869566, 'recall': 0.8901098901098901, 'f1': 0.7864077669902914, 'number': 91} | {'precision': 0.9209706509263814, 'recall': 0.9859575215025452, 'f1': 0.9523567310952866, 'number': 5697} | 0.8355            | 0.8914         | 0.8625     | 0.8375           |
+| 0.8695        | 1.98  | 10000 | 0.8788          | {'precision': 0.6812743986903412, 'recall': 0.8032665181885672, 'f1': 0.7372581084764241, 'number': 6735} | {'precision': 0.7975521005623553, 'recall': 0.821838427451426, 'f1': 0.8095131505316173, 'number': 8801}  | {'precision': 0.9779074614422676, 'recall': 0.9929458239277652, 'f1': 0.9853692684634231, 'number': 7088} | {'precision': 0.6267605633802817, 'recall': 0.978021978021978, 'f1': 0.7639484978540774, 'number': 91}  | {'precision': 0.9206036745406824, 'recall': 0.9850798665964543, 'f1': 0.9517510387518019, 'number': 5697} | 0.8337            | 0.8934         | 0.8625     | 0.8376           |
+| 0.8537        | 2.18  | 11000 | 0.8804          | {'precision': 0.6863314805457301, 'recall': 0.8066815144766147, 'f1': 0.741655859668282, 'number': 6735}  | {'precision': 0.8018565587357719, 'recall': 0.8244517668446767, 'f1': 0.8129971988795517, 'number': 8801} | {'precision': 0.9830627099664053, 'recall': 0.9908295711060948, 'f1': 0.9869308600337269, 'number': 7088} | {'precision': 0.6825396825396826, 'recall': 0.945054945054945, 'f1': 0.792626728110599, 'number': 91}   | {'precision': 0.9248306624814142, 'recall': 0.9826224328593997, 'f1': 0.9528510638297872, 'number': 5697} | 0.8385            | 0.8938         | 0.8653     | 0.8384           |
+| 0.854         | 2.38  | 12000 | 0.8817          | {'precision': 0.6863779033270558, 'recall': 0.8117297698589458, 'f1': 0.7438095238095238, 'number': 6735} | {'precision': 0.8055925432756325, 'recall': 0.8249062606521986, 'f1': 0.8151350137539999, 'number': 8801} | {'precision': 0.9833426651735723, 'recall': 0.9911117381489842, 'f1': 0.9872119168071951, 'number': 7088} | {'precision': 0.6742424242424242, 'recall': 0.978021978021978, 'f1': 0.7982062780269058, 'number': 91}  | {'precision': 0.9206687428290444, 'recall': 0.9859575215025452, 'f1': 0.9521952873368368, 'number': 5697} | 0.8387            | 0.8960         | 0.8664     | 0.8390           |
+| 0.8582        | 2.57  | 13000 | 0.8746          | {'precision': 0.6879990019960079, 'recall': 0.8188567186340014, 'f1': 0.7477459155311504, 'number': 6735} | {'precision': 0.8027563395810364, 'recall': 0.8272923531416885, 'f1': 0.8148396844049018, 'number': 8801} | {'precision': 0.9822476935979871, 'recall': 0.9913939051918735, 'f1': 0.9867996067967982, 'number': 7088} | {'precision': 0.6693548387096774, 'recall': 0.9120879120879121, 'f1': 0.772093023255814, 'number': 91}  | {'precision': 0.9260487481346377, 'recall': 0.9803405301035633, 'f1': 0.9524215552523875, 'number': 5697} | 0.8387            | 0.8972         | 0.8669     | 0.8402           |
+| 0.8554        | 2.77  | 14000 | 0.8743          | {'precision': 0.6870807453416149, 'recall': 0.8212323682256867, 'f1': 0.7481907338518768, 'number': 6735} | {'precision': 0.8064945140197274, 'recall': 0.8268378593341665, 'f1': 0.8165394973070018, 'number': 8801} | {'precision': 0.9841692350798543, 'recall': 0.9911117381489842, 'f1': 0.9876282862364684, 'number': 7088} | {'precision': 0.672, 'recall': 0.9230769230769231, 'f1': 0.7777777777777778, 'number': 91}              | {'precision': 0.923507155782201, 'recall': 0.9854309285588907, 'f1': 0.9534646739130435, 'number': 5697}  | 0.8394            | 0.8986         | 0.8680     | 0.8416           |
+| 0.86          | 2.97  | 15000 | 0.8735          | {'precision': 0.6898646083765658, 'recall': 0.8095025983667409, 'f1': 0.7449105068998496, 'number': 6735} | {'precision': 0.8031156778256546, 'recall': 0.8259288717191229, 'f1': 0.8143625364104862, 'number': 8801} | {'precision': 0.9833473271760426, 'recall': 0.9913939051918735, 'f1': 0.9873542222846705, 'number': 7088} | {'precision': 0.6611570247933884, 'recall': 0.8791208791208791, 'f1': 0.7547169811320755, 'number': 91} | {'precision': 0.9261034881798644, 'recall': 0.9833245567842724, 'f1': 0.9538566320449514, 'number': 5697} | 0.8401            | 0.8950         | 0.8667     | 0.8423           |
+| 0.845         | 3.17  | 16000 | 0.8782          | {'precision': 0.7035061991734436, 'recall': 0.7835189309576838, 'f1': 0.7413599325653274, 'number': 6735} | {'precision': 0.7948126167710737, 'recall': 0.8217248039995455, 'f1': 0.8080446927374302, 'number': 8801} | {'precision': 0.982394858180802, 'recall': 0.9919582392776524, 'f1': 0.9871533871533871, 'number': 7088}  | {'precision': 0.719626168224299, 'recall': 0.8461538461538461, 'f1': 0.7777777777777778, 'number': 91}  | {'precision': 0.9267119880616813, 'recall': 0.981042654028436, 'f1': 0.9531036834924966, 'number': 5697}  | 0.8432            | 0.8872         | 0.8646     | 0.8397           |
+| 0.846         | 3.37  | 17000 | 0.8759          | {'precision': 0.6963411491883535, 'recall': 0.8025241276911655, 'f1': 0.7456715182451542, 'number': 6735} | {'precision': 0.7992290748898678, 'recall': 0.8245653902965572, 'f1': 0.8116995693753145, 'number': 8801} | {'precision': 0.984164798206278, 'recall': 0.9908295711060948, 'f1': 0.9874859392575928, 'number': 7088}  | {'precision': 0.6694214876033058, 'recall': 0.8901098901098901, 'f1': 0.7641509433962264, 'number': 91} | {'precision': 0.9245874587458746, 'recall': 0.9835000877654906, 'f1': 0.9531343029684443, 'number': 5697} | 0.8412            | 0.8929         | 0.8663     | 0.8403           |
+| 0.8392        | 3.56  | 18000 | 0.8759          | {'precision': 0.7022442588726514, 'recall': 0.799109131403118, 'f1': 0.7475519133273144, 'number': 6735}  | {'precision': 0.8000660211267606, 'recall': 0.8261561186228837, 'f1': 0.8129017832187377, 'number': 8801} | {'precision': 0.9823997765050985, 'recall': 0.9922404063205418, 'f1': 0.987295570997403, 'number': 7088}  | {'precision': 0.6890756302521008, 'recall': 0.9010989010989011, 'f1': 0.7809523809523808, 'number': 91} | {'precision': 0.9239380968060587, 'recall': 0.9850798665964543, 'f1': 0.9535298615240847, 'number': 5697} | 0.8431            | 0.8933         | 0.8675     | 0.8409           |
+| 0.8375        | 3.76  | 19000 | 0.8780          | {'precision': 0.6947714900620332, 'recall': 0.8148478099480326, 'f1': 0.7500341670083366, 'number': 6735} | {'precision': 0.8054323725055432, 'recall': 0.8254743779116009, 'f1': 0.8153302283822457, 'number': 8801} | {'precision': 0.9837648705388383, 'recall': 0.991676072234763, 'f1': 0.9877046300850137, 'number': 7088}  | {'precision': 0.6864406779661016, 'recall': 0.8901098901098901, 'f1': 0.7751196172248803, 'number': 91} | {'precision': 0.9236477572559367, 'recall': 0.9831490258030542, 'f1': 0.9524700280588385, 'number': 5697} | 0.8419            | 0.8962         | 0.8682     | 0.8413           |
+| 0.8366        | 3.96  | 20000 | 0.8742          | {'precision': 0.7003211303789338, 'recall': 0.8095025983667409, 'f1': 0.7509641873278236, 'number': 6735} | {'precision': 0.804251550044287, 'recall': 0.8253607544597205, 'f1': 0.8146694330735154, 'number': 8801}  | {'precision': 0.9832073887489504, 'recall': 0.9912528216704289, 'f1': 0.9872137136433891, 'number': 7088} | {'precision': 0.7053571428571429, 'recall': 0.8681318681318682, 'f1': 0.7783251231527095, 'number': 91} | {'precision': 0.9234189723320159, 'recall': 0.9842022116903634, 'f1': 0.9528422125924038, 'number': 5697} | 0.8435            | 0.8950         | 0.8685     | 0.8417           |
+| 0.8189        | 4.16  | 21000 | 0.8799          | {'precision': 0.7027131284557027, 'recall': 0.8114328136599851, 'f1': 0.7531697905181918, 'number': 6735} | {'precision': 0.8056294326241135, 'recall': 0.8260424951710033, 'f1': 0.8157082748948107, 'number': 8801} | {'precision': 0.9825345815285734, 'recall': 0.9920993227990971, 'f1': 0.9872937872937874, 'number': 7088} | {'precision': 0.6864406779661016, 'recall': 0.8901098901098901, 'f1': 0.7751196172248803, 'number': 91} | {'precision': 0.9251195777667821, 'recall': 0.9845532736527998, 'f1': 0.9539115646258504, 'number': 5697} | 0.8447            | 0.8960         | 0.8696     | 0.8425           |
+| 0.8269        | 4.36  | 22000 | 0.8781          | {'precision': 0.6995086630462891, 'recall': 0.8032665181885672, 'f1': 0.7478056534660309, 'number': 6735} | {'precision': 0.8004192409532216, 'recall': 0.8243381433927963, 'f1': 0.8122026308424294, 'number': 8801} | {'precision': 0.9833403331933361, 'recall': 0.9909706546275395, 'f1': 0.987140749068934, 'number': 7088}  | {'precision': 0.7079646017699115, 'recall': 0.8791208791208791, 'f1': 0.7843137254901961, 'number': 91} | {'precision': 0.9244473771032663, 'recall': 0.9836756187467088, 'f1': 0.9531422740028915, 'number': 5697} | 0.8425            | 0.8930         | 0.8670     | 0.8418           |
+| 0.829         | 4.55  | 23000 | 0.8794          | {'precision': 0.70192058136517, 'recall': 0.8031180400890868, 'f1': 0.7491170971539367, 'number': 6735}   | {'precision': 0.7987892129884425, 'recall': 0.8245653902965572, 'f1': 0.8114726601811473, 'number': 8801} | {'precision': 0.9836226203807391, 'recall': 0.9913939051918735, 'f1': 0.9874929735806632, 'number': 7088} | {'precision': 0.6991150442477876, 'recall': 0.8681318681318682, 'f1': 0.7745098039215685, 'number': 91} | {'precision': 0.9249050998514606, 'recall': 0.9836756187467088, 'f1': 0.9533855052739026, 'number': 5697} | 0.8429            | 0.8931         | 0.8673     | 0.8422           |
+| 0.8183        | 4.75  | 24000 | 0.8815          | {'precision': 0.6988397296952696, 'recall': 0.8138084632516703, 'f1': 0.7519550006859651, 'number': 6735} | {'precision': 0.806115665854199, 'recall': 0.826724235882286, 'f1': 0.8162898973467212, 'number': 8801}   | {'precision': 0.9834757036829576, 'recall': 0.9908295711060948, 'f1': 0.9871389415981446, 'number': 7088} | {'precision': 0.6837606837606838, 'recall': 0.8791208791208791, 'f1': 0.7692307692307692, 'number': 91} | {'precision': 0.9244473771032663, 'recall': 0.9836756187467088, 'f1': 0.9531422740028915, 'number': 5697} | 0.8435            | 0.8962         | 0.8691     | 0.8428           |
+| 0.8201        | 4.95  | 25000 | 0.8808          | {'precision': 0.7003986112897004, 'recall': 0.8087602078693392, 'f1': 0.7506890848952591, 'number': 6735} | {'precision': 0.8026315789473685, 'recall': 0.8247926372003181, 'f1': 0.8135612216307089, 'number': 8801} | {'precision': 0.9834849545136459, 'recall': 0.9913939051918735, 'f1': 0.9874235930583853, 'number': 7088} | {'precision': 0.6923076923076923, 'recall': 0.8901098901098901, 'f1': 0.7788461538461537, 'number': 91} | {'precision': 0.9247400561148704, 'recall': 0.9835000877654906, 'f1': 0.9532153793807416, 'number': 5697} | 0.8432            | 0.8946         | 0.8682     | 0.8429           |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

all_results.json

@@ -0,0 +1,41 @@
+{
+    "epoch": 5.0,
+    "eval_COMMENT": {
+        "f1": 0.7559428461587748,
+        "number": 7184,
+        "precision": 0.700344295381693,
+        "recall": 0.8211302895322939
+    },
+    "eval_NAME": {
+        "f1": 0.8218668650055783,
+        "number": 9303,
+        "precision": 0.8125,
+        "recall": 0.8314522197140707
+    },
+    "eval_QTY": {
+        "f1": 0.9895239358175308,
+        "number": 7522,
+        "precision": 0.987037037037037,
+        "recall": 0.9920233980324382
+    },
+    "eval_RANGE_END": {
+        "f1": 0.8267716535433071,
+        "number": 112,
+        "precision": 0.7394366197183099,
+        "recall": 0.9375
+    },
+    "eval_UNIT": {
+        "f1": 0.9567672205194386,
+        "number": 6009,
+        "precision": 0.9283142901862577,
+        "recall": 0.9870194707938093
+    },
+    "eval_loss": 0.8647457957267761,
+    "eval_overall_accuracy": 0.8468235935653913,
+    "eval_overall_f1": 0.8729168007206745,
+    "eval_overall_precision": 0.8469750889679716,
+    "eval_overall_recall": 0.9004978426817126,
+    "eval_runtime": 13.1391,
+    "eval_samples_per_second": 681.476,
+    "eval_steps_per_second": 21.31
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "thenlper/gte-small",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "O",
+    "1": "B-COMMENT",
+    "2": "I-COMMENT",
+    "3": "B-NAME",
+    "4": "I-NAME",
+    "5": "B-RANGE_END",
+    "6": "I-RANGE_END",
+    "7": "B-QTY",
+    "8": "I-QTY",
+    "9": "B-UNIT",
+    "10": "I-UNIT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "B-COMMENT": 1,
+    "B-NAME": 3,
+    "B-QTY": 7,
+    "B-RANGE_END": 5,
+    "B-UNIT": 9,
+    "I-COMMENT": 2,
+    "I-NAME": 4,
+    "I-QTY": 8,
+    "I-RANGE_END": 6,
+    "I-UNIT": 10,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45538a882f081a9f814c68576f799747a74b472d07d82376be44af8c4c3977a
+size 132933289

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

test_results.json

@@ -0,0 +1,41 @@
+{
+    "epoch": 5.0,
+    "eval_COMMENT": {
+        "f1": 0.7559428461587748,
+        "number": 7184,
+        "precision": 0.700344295381693,
+        "recall": 0.8211302895322939
+    },
+    "eval_NAME": {
+        "f1": 0.8218668650055783,
+        "number": 9303,
+        "precision": 0.8125,
+        "recall": 0.8314522197140707
+    },
+    "eval_QTY": {
+        "f1": 0.9895239358175308,
+        "number": 7522,
+        "precision": 0.987037037037037,
+        "recall": 0.9920233980324382
+    },
+    "eval_RANGE_END": {
+        "f1": 0.8267716535433071,
+        "number": 112,
+        "precision": 0.7394366197183099,
+        "recall": 0.9375
+    },
+    "eval_UNIT": {
+        "f1": 0.9567672205194386,
+        "number": 6009,
+        "precision": 0.9283142901862577,
+        "recall": 0.9870194707938093
+    },
+    "eval_loss": 0.8647457957267761,
+    "eval_overall_accuracy": 0.8468235935653913,
+    "eval_overall_f1": 0.8729168007206745,
+    "eval_overall_precision": 0.8469750889679716,
+    "eval_overall_recall": 0.9004978426817126,
+    "eval_runtime": 13.1391,
+    "eval_samples_per_second": 681.476,
+    "eval_steps_per_second": 21.31
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,41 @@
+{
+    "epoch": 5.0,
+    "eval_COMMENT": {
+        "f1": 0.7814673021329791,
+        "number": 129869,
+        "precision": 0.7252173569135648,
+        "recall": 0.8471767704379028
+    },
+    "eval_NAME": {
+        "f1": 0.8310644366653702,
+        "number": 167696,
+        "precision": 0.8214310678254386,
+        "recall": 0.8409264383169545
+    },
+    "eval_QTY": {
+        "f1": 0.988619426272238,
+        "number": 135854,
+        "precision": 0.9861359308627509,
+        "recall": 0.9911154621873481
+    },
+    "eval_RANGE_END": {
+        "f1": 0.774937343358396,
+        "number": 1661,
+        "precision": 0.6638042078145127,
+        "recall": 0.9307645996387718
+    },
+    "eval_UNIT": {
+        "f1": 0.9579896412814118,
+        "number": 108847,
+        "precision": 0.9311346607464964,
+        "recall": 0.9864396813876358
+    },
+    "eval_loss": 0.827319324016571,
+    "eval_overall_accuracy": 0.8628335736925197,
+    "eval_overall_f1": 0.8820491969187504,
+    "eval_overall_precision": 0.8563627360336308,
+    "eval_overall_recall": 0.9093242291704585,
+    "eval_runtime": 229.2348,
+    "eval_samples_per_second": 704.967,
+    "eval_steps_per_second": 22.034
+}

trainer_state.json

@@ -0,0 +1,1378 @@
+{
+  "best_metric": 0.873456597328186,
+  "best_model_checkpoint": "nyt-ingredient-tagger-gte-small/checkpoint-15000",
+  "epoch": 5.0,
+  "eval_steps": 1000,
+  "global_step": 25255,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.9010097010492975e-05,
+      "loss": 1.1066,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.802019402098595e-05,
+      "loss": 0.9427,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "eval_COMMENT": {
+        "f1": 0.6827173347214992,
+        "number": 6735,
+        "precision": 0.6076682497393722,
+        "recall": 0.7789161098737936
+      },
+      "eval_NAME": {
+        "f1": 0.7975022301516503,
+        "number": 8801,
+        "precision": 0.7829228243021347,
+        "recall": 0.8126349278491081
+      },
+      "eval_QTY": {
+        "f1": 0.9832785279507451,
+        "number": 7088,
+        "precision": 0.97529493407356,
+        "recall": 0.9913939051918735
+      },
+      "eval_RANGE_END": {
+        "f1": 0.6793893129770994,
+        "number": 91,
+        "precision": 0.52046783625731,
+        "recall": 0.978021978021978
+      },
+      "eval_UNIT": {
+        "f1": 0.9474663734032653,
+        "number": 5697,
+        "precision": 0.914435009797518,
+        "recall": 0.982973494821836
+      },
+      "eval_loss": 0.9320821166038513,
+      "eval_overall_accuracy": 0.8183442525312686,
+      "eval_overall_f1": 0.8416219839142092,
+      "eval_overall_precision": 0.8031853652296277,
+      "eval_overall_recall": 0.883922286357877,
+      "eval_runtime": 12.4448,
+      "eval_samples_per_second": 683.5,
+      "eval_steps_per_second": 21.374,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.703029103147892e-05,
+      "loss": 0.9333,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.6040388041971886e-05,
+      "loss": 0.9169,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4,
+      "eval_COMMENT": {
+        "f1": 0.7030077684084721,
+        "number": 6735,
+        "precision": 0.6358395387941388,
+        "recall": 0.7860430586488493
+      },
+      "eval_NAME": {
+        "f1": 0.798910626945309,
+        "number": 8801,
+        "precision": 0.781960613643782,
+        "recall": 0.8166117486649245
+      },
+      "eval_QTY": {
+        "f1": 0.9835744740336898,
+        "number": 7088,
+        "precision": 0.9746502285635129,
+        "recall": 0.9926636568848759
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7543859649122806,
+        "number": 91,
+        "precision": 0.6277372262773723,
+        "recall": 0.945054945054945
+      },
+      "eval_UNIT": {
+        "f1": 0.9503173931443081,
+        "number": 5697,
+        "precision": 0.9176201372997712,
+        "recall": 0.9854309285588907
+      },
+      "eval_loss": 0.9112022519111633,
+      "eval_overall_accuracy": 0.8256066398970201,
+      "eval_overall_f1": 0.8490143595441308,
+      "eval_overall_precision": 0.8136878448581847,
+      "eval_overall_recall": 0.8875475151344502,
+      "eval_runtime": 12.0886,
+      "eval_samples_per_second": 703.64,
+      "eval_steps_per_second": 22.004,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.505048505246486e-05,
+      "loss": 0.9126,
+      "step": 2500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.406058206295783e-05,
+      "loss": 0.9,
+      "step": 3000
+    },
+    {
+      "epoch": 0.59,
+      "eval_COMMENT": {
+        "f1": 0.7219525171244263,
+        "number": 6735,
+        "precision": 0.6538183570224042,
+        "recall": 0.8059391239792131
+      },
+      "eval_NAME": {
+        "f1": 0.8061383928571427,
+        "number": 8801,
+        "precision": 0.7920824651825858,
+        "recall": 0.8207021929326213
+      },
+      "eval_QTY": {
+        "f1": 0.9870641169853768,
+        "number": 7088,
+        "precision": 0.9837443946188341,
+        "recall": 0.9904063205417607
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7309644670050762,
+        "number": 91,
+        "precision": 0.6792452830188679,
+        "recall": 0.7912087912087912
+      },
+      "eval_UNIT": {
+        "f1": 0.9483108108108108,
+        "number": 5697,
+        "precision": 0.9138857235878235,
+        "recall": 0.9854309285588907
+      },
+      "eval_loss": 0.902090847492218,
+      "eval_overall_accuracy": 0.8302368921593114,
+      "eval_overall_f1": 0.856395015029214,
+      "eval_overall_precision": 0.8231188729468285,
+      "eval_overall_recall": 0.8924750105589188,
+      "eval_runtime": 14.5748,
+      "eval_samples_per_second": 583.612,
+      "eval_steps_per_second": 18.251,
+      "step": 3000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.3070679073450804e-05,
+      "loss": 0.9058,
+      "step": 3500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.208077608394378e-05,
+      "loss": 0.9061,
+      "step": 4000
+    },
+    {
+      "epoch": 0.79,
+      "eval_COMMENT": {
+        "f1": 0.7202272266179753,
+        "number": 6735,
+        "precision": 0.6613263785394933,
+        "recall": 0.7906458797327395
+      },
+      "eval_NAME": {
+        "f1": 0.8081158124196521,
+        "number": 8801,
+        "precision": 0.7952695269526953,
+        "recall": 0.821383933643904
+      },
+      "eval_QTY": {
+        "f1": 0.9869014084507043,
+        "number": 7088,
+        "precision": 0.985236220472441,
+        "recall": 0.9885722347629797
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7592592592592593,
+        "number": 91,
+        "precision": 0.656,
+        "recall": 0.9010989010989011
+      },
+      "eval_UNIT": {
+        "f1": 0.9522355137015356,
+        "number": 5697,
+        "precision": 0.9215106732348112,
+        "recall": 0.9850798665964543
+      },
+      "eval_loss": 0.8911505341529846,
+      "eval_overall_accuracy": 0.8325616246229515,
+      "eval_overall_f1": 0.857831898235424,
+      "eval_overall_precision": 0.8288752502543569,
+      "eval_overall_recall": 0.8888849781782345,
+      "eval_runtime": 12.1725,
+      "eval_samples_per_second": 698.791,
+      "eval_steps_per_second": 21.853,
+      "step": 4000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.109087309443675e-05,
+      "loss": 0.8962,
+      "step": 4500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.010097010492972e-05,
+      "loss": 0.8889,
+      "step": 5000
+    },
+    {
+      "epoch": 0.99,
+      "eval_COMMENT": {
+        "f1": 0.7147275101367603,
+        "number": 6735,
+        "precision": 0.6653019447287615,
+        "recall": 0.7720861172976986
+      },
+      "eval_NAME": {
+        "f1": 0.8085439498993513,
+        "number": 8801,
+        "precision": 0.7959925134867335,
+        "recall": 0.8214975570957845
+      },
+      "eval_QTY": {
+        "f1": 0.9872508276396421,
+        "number": 7088,
+        "precision": 0.9857926571951048,
+        "recall": 0.9887133182844243
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7623318385650225,
+        "number": 91,
+        "precision": 0.6439393939393939,
+        "recall": 0.9340659340659341
+      },
+      "eval_UNIT": {
+        "f1": 0.9522514868309261,
+        "number": 5697,
+        "precision": 0.9227729293594599,
+        "recall": 0.9836756187467088
+      },
+      "eval_loss": 0.8908107876777649,
+      "eval_overall_accuracy": 0.8310630367538281,
+      "eval_overall_f1": 0.8572110874200426,
+      "eval_overall_precision": 0.8316618674080694,
+      "eval_overall_recall": 0.8843798395044348,
+      "eval_runtime": 12.1451,
+      "eval_samples_per_second": 700.364,
+      "eval_steps_per_second": 21.902,
+      "step": 5000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.911106711542269e-05,
+      "loss": 0.8786,
+      "step": 5500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 3.812116412591566e-05,
+      "loss": 0.88,
+      "step": 6000
+    },
+    {
+      "epoch": 1.19,
+      "eval_COMMENT": {
+        "f1": 0.7254114813327982,
+        "number": 6735,
+        "precision": 0.660211910851297,
+        "recall": 0.8048997772828508
+      },
+      "eval_NAME": {
+        "f1": 0.8067433292397008,
+        "number": 8801,
+        "precision": 0.7929331723910896,
+        "recall": 0.8210430632882627
+      },
+      "eval_QTY": {
+        "f1": 0.9868633649455567,
+        "number": 7088,
+        "precision": 0.9827899818105499,
+        "recall": 0.9909706546275395
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7631578947368421,
+        "number": 91,
+        "precision": 0.635036496350365,
+        "recall": 0.9560439560439561
+      },
+      "eval_UNIT": {
+        "f1": 0.9526315789473684,
+        "number": 5697,
+        "precision": 0.9224067072168338,
+        "recall": 0.984904335615236
+      },
+      "eval_loss": 0.8873026371002197,
+      "eval_overall_accuracy": 0.8337912351822321,
+      "eval_overall_f1": 0.8584674212814917,
+      "eval_overall_precision": 0.8265941155387573,
+      "eval_overall_recall": 0.8928973673095875,
+      "eval_runtime": 13.0658,
+      "eval_samples_per_second": 651.014,
+      "eval_steps_per_second": 20.359,
+      "step": 6000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.7131261136408633e-05,
+      "loss": 0.8761,
+      "step": 6500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 3.6141358146901606e-05,
+      "loss": 0.8751,
+      "step": 7000
+    },
+    {
+      "epoch": 1.39,
+      "eval_COMMENT": {
+        "f1": 0.7309149972929073,
+        "number": 6735,
+        "precision": 0.6715582638975252,
+        "recall": 0.8017817371937639
+      },
+      "eval_NAME": {
+        "f1": 0.8121178120617111,
+        "number": 8801,
+        "precision": 0.8020833333333334,
+        "recall": 0.8224065447108283
+      },
+      "eval_QTY": {
+        "f1": 0.9871903153153153,
+        "number": 7088,
+        "precision": 0.9849719101123595,
+        "recall": 0.9894187358916479
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7565217391304349,
+        "number": 91,
+        "precision": 0.6258992805755396,
+        "recall": 0.9560439560439561
+      },
+      "eval_UNIT": {
+        "f1": 0.9523647209203238,
+        "number": 5697,
+        "precision": 0.9254720105995363,
+        "recall": 0.9808671230472178
+      },
+      "eval_loss": 0.8865671157836914,
+      "eval_overall_accuracy": 0.834847931756614,
+      "eval_overall_f1": 0.8618096437200122,
+      "eval_overall_precision": 0.8341347737303207,
+      "eval_overall_recall": 0.8913839222863579,
+      "eval_runtime": 12.663,
+      "eval_samples_per_second": 671.721,
+      "eval_steps_per_second": 21.006,
+      "step": 7000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.515145515739457e-05,
+      "loss": 0.8836,
+      "step": 7500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.416155216788755e-05,
+      "loss": 0.8816,
+      "step": 8000
+    },
+    {
+      "epoch": 1.58,
+      "eval_COMMENT": {
+        "f1": 0.7336898395721925,
+        "number": 6735,
+        "precision": 0.6672340425531915,
+        "recall": 0.8148478099480326
+      },
+      "eval_NAME": {
+        "f1": 0.8090705487122061,
+        "number": 8801,
+        "precision": 0.797549398388343,
+        "recall": 0.8209294398363822
+      },
+      "eval_QTY": {
+        "f1": 0.9869745828346124,
+        "number": 7088,
+        "precision": 0.9851018973998594,
+        "recall": 0.988854401805869
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7623318385650225,
+        "number": 91,
+        "precision": 0.6439393939393939,
+        "recall": 0.9340659340659341
+      },
+      "eval_UNIT": {
+        "f1": 0.9534507701472215,
+        "number": 5697,
+        "precision": 0.9253386190948133,
+        "recall": 0.9833245567842724
+      },
+      "eval_loss": 0.8822705745697021,
+      "eval_overall_accuracy": 0.835962266325962,
+      "eval_overall_f1": 0.8613658321609573,
+      "eval_overall_precision": 0.8307667157103155,
+      "eval_overall_recall": 0.8943052231451499,
+      "eval_runtime": 12.6561,
+      "eval_samples_per_second": 672.089,
+      "eval_steps_per_second": 21.018,
+      "step": 8000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.317164917838052e-05,
+      "loss": 0.8785,
+      "step": 8500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.218174618887349e-05,
+      "loss": 0.8756,
+      "step": 9000
+    },
+    {
+      "epoch": 1.78,
+      "eval_COMMENT": {
+        "f1": 0.7321063394683027,
+        "number": 6735,
+        "precision": 0.6767485822306238,
+        "recall": 0.7973273942093542
+      },
+      "eval_NAME": {
+        "f1": 0.8122265844083006,
+        "number": 8801,
+        "precision": 0.8019714254070218,
+        "recall": 0.8227474150664698
+      },
+      "eval_QTY": {
+        "f1": 0.9867829021372329,
+        "number": 7088,
+        "precision": 0.9834641255605381,
+        "recall": 0.9901241534988713
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7864077669902914,
+        "number": 91,
+        "precision": 0.7043478260869566,
+        "recall": 0.8901098901098901
+      },
+      "eval_UNIT": {
+        "f1": 0.9523567310952866,
+        "number": 5697,
+        "precision": 0.9209706509263814,
+        "recall": 0.9859575215025452
+      },
+      "eval_loss": 0.8817200660705566,
+      "eval_overall_accuracy": 0.8375377048550404,
+      "eval_overall_f1": 0.8625481047576883,
+      "eval_overall_precision": 0.8354885531437619,
+      "eval_overall_recall": 0.891419118682247,
+      "eval_runtime": 13.1407,
+      "eval_samples_per_second": 647.302,
+      "eval_steps_per_second": 20.242,
+      "step": 9000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 3.119184319936647e-05,
+      "loss": 0.8739,
+      "step": 9500
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.0201940209859435e-05,
+      "loss": 0.8695,
+      "step": 10000
+    },
+    {
+      "epoch": 1.98,
+      "eval_COMMENT": {
+        "f1": 0.7372581084764241,
+        "number": 6735,
+        "precision": 0.6812743986903412,
+        "recall": 0.8032665181885672
+      },
+      "eval_NAME": {
+        "f1": 0.8095131505316173,
+        "number": 8801,
+        "precision": 0.7975521005623553,
+        "recall": 0.821838427451426
+      },
+      "eval_QTY": {
+        "f1": 0.9853692684634231,
+        "number": 7088,
+        "precision": 0.9779074614422676,
+        "recall": 0.9929458239277652
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7639484978540774,
+        "number": 91,
+        "precision": 0.6267605633802817,
+        "recall": 0.978021978021978
+      },
+      "eval_UNIT": {
+        "f1": 0.9517510387518019,
+        "number": 5697,
+        "precision": 0.9206036745406824,
+        "recall": 0.9850798665964543
+      },
+      "eval_loss": 0.8788286447525024,
+      "eval_overall_accuracy": 0.8376145555149955,
+      "eval_overall_f1": 0.8624972390709686,
+      "eval_overall_precision": 0.8337001149614058,
+      "eval_overall_recall": 0.8933549204561453,
+      "eval_runtime": 12.7467,
+      "eval_samples_per_second": 667.312,
+      "eval_steps_per_second": 20.868,
+      "step": 10000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.9212037220352405e-05,
+      "loss": 0.8595,
+      "step": 10500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 2.8222134230845377e-05,
+      "loss": 0.8537,
+      "step": 11000
+    },
+    {
+      "epoch": 2.18,
+      "eval_COMMENT": {
+        "f1": 0.741655859668282,
+        "number": 6735,
+        "precision": 0.6863314805457301,
+        "recall": 0.8066815144766147
+      },
+      "eval_NAME": {
+        "f1": 0.8129971988795517,
+        "number": 8801,
+        "precision": 0.8018565587357719,
+        "recall": 0.8244517668446767
+      },
+      "eval_QTY": {
+        "f1": 0.9869308600337269,
+        "number": 7088,
+        "precision": 0.9830627099664053,
+        "recall": 0.9908295711060948
+      },
+      "eval_RANGE_END": {
+        "f1": 0.792626728110599,
+        "number": 91,
+        "precision": 0.6825396825396826,
+        "recall": 0.945054945054945
+      },
+      "eval_UNIT": {
+        "f1": 0.9528510638297872,
+        "number": 5697,
+        "precision": 0.9248306624814142,
+        "recall": 0.9826224328593997
+      },
+      "eval_loss": 0.8804447650909424,
+      "eval_overall_accuracy": 0.8384022747795347,
+      "eval_overall_f1": 0.8652810902896081,
+      "eval_overall_precision": 0.8384838880084522,
+      "eval_overall_recall": 0.8938476699985921,
+      "eval_runtime": 13.7729,
+      "eval_samples_per_second": 617.589,
+      "eval_steps_per_second": 19.313,
+      "step": 11000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.7232231241338353e-05,
+      "loss": 0.8543,
+      "step": 11500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.6242328251831323e-05,
+      "loss": 0.854,
+      "step": 12000
+    },
+    {
+      "epoch": 2.38,
+      "eval_COMMENT": {
+        "f1": 0.7438095238095238,
+        "number": 6735,
+        "precision": 0.6863779033270558,
+        "recall": 0.8117297698589458
+      },
+      "eval_NAME": {
+        "f1": 0.8151350137539999,
+        "number": 8801,
+        "precision": 0.8055925432756325,
+        "recall": 0.8249062606521986
+      },
+      "eval_QTY": {
+        "f1": 0.9872119168071951,
+        "number": 7088,
+        "precision": 0.9833426651735723,
+        "recall": 0.9911117381489842
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7982062780269058,
+        "number": 91,
+        "precision": 0.6742424242424242,
+        "recall": 0.978021978021978
+      },
+      "eval_UNIT": {
+        "f1": 0.9521952873368368,
+        "number": 5697,
+        "precision": 0.9206687428290444,
+        "recall": 0.9859575215025452
+      },
+      "eval_loss": 0.8816655278205872,
+      "eval_overall_accuracy": 0.8389594420642087,
+      "eval_overall_f1": 0.8664193581322533,
+      "eval_overall_precision": 0.8387033010476379,
+      "eval_overall_recall": 0.8960298465437139,
+      "eval_runtime": 12.7157,
+      "eval_samples_per_second": 668.937,
+      "eval_steps_per_second": 20.919,
+      "step": 12000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 2.5252425262324292e-05,
+      "loss": 0.8609,
+      "step": 12500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.4262522272817265e-05,
+      "loss": 0.8582,
+      "step": 13000
+    },
+    {
+      "epoch": 2.57,
+      "eval_COMMENT": {
+        "f1": 0.7477459155311504,
+        "number": 6735,
+        "precision": 0.6879990019960079,
+        "recall": 0.8188567186340014
+      },
+      "eval_NAME": {
+        "f1": 0.8148396844049018,
+        "number": 8801,
+        "precision": 0.8027563395810364,
+        "recall": 0.8272923531416885
+      },
+      "eval_QTY": {
+        "f1": 0.9867996067967982,
+        "number": 7088,
+        "precision": 0.9822476935979871,
+        "recall": 0.9913939051918735
+      },
+      "eval_RANGE_END": {
+        "f1": 0.772093023255814,
+        "number": 91,
+        "precision": 0.6693548387096774,
+        "recall": 0.9120879120879121
+      },
+      "eval_UNIT": {
+        "f1": 0.9524215552523875,
+        "number": 5697,
+        "precision": 0.9260487481346377,
+        "recall": 0.9803405301035633
+      },
+      "eval_loss": 0.8745654225349426,
+      "eval_overall_accuracy": 0.8401890526234894,
+      "eval_overall_f1": 0.8669376094682606,
+      "eval_overall_precision": 0.8386576739595328,
+      "eval_overall_recall": 0.897191327608053,
+      "eval_runtime": 10.2599,
+      "eval_samples_per_second": 829.055,
+      "eval_steps_per_second": 25.926,
+      "step": 13000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.3272619283310237e-05,
+      "loss": 0.8617,
+      "step": 13500
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.2282716293803206e-05,
+      "loss": 0.8554,
+      "step": 14000
+    },
+    {
+      "epoch": 2.77,
+      "eval_COMMENT": {
+        "f1": 0.7481907338518768,
+        "number": 6735,
+        "precision": 0.6870807453416149,
+        "recall": 0.8212323682256867
+      },
+      "eval_NAME": {
+        "f1": 0.8165394973070018,
+        "number": 8801,
+        "precision": 0.8064945140197274,
+        "recall": 0.8268378593341665
+      },
+      "eval_QTY": {
+        "f1": 0.9876282862364684,
+        "number": 7088,
+        "precision": 0.9841692350798543,
+        "recall": 0.9911117381489842
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7777777777777778,
+        "number": 91,
+        "precision": 0.672,
+        "recall": 0.9230769230769231
+      },
+      "eval_UNIT": {
+        "f1": 0.9534646739130435,
+        "number": 5697,
+        "precision": 0.923507155782201,
+        "recall": 0.9854309285588907
+      },
+      "eval_loss": 0.8742881417274475,
+      "eval_overall_accuracy": 0.8416107898326577,
+      "eval_overall_f1": 0.8680027878355177,
+      "eval_overall_precision": 0.8394213381555153,
+      "eval_overall_recall": 0.8985991834436153,
+      "eval_runtime": 10.2908,
+      "eval_samples_per_second": 826.561,
+      "eval_steps_per_second": 25.848,
+      "step": 14000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.129281330429618e-05,
+      "loss": 0.8553,
+      "step": 14500
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 2.0302910314789152e-05,
+      "loss": 0.86,
+      "step": 15000
+    },
+    {
+      "epoch": 2.97,
+      "eval_COMMENT": {
+        "f1": 0.7449105068998496,
+        "number": 6735,
+        "precision": 0.6898646083765658,
+        "recall": 0.8095025983667409
+      },
+      "eval_NAME": {
+        "f1": 0.8143625364104862,
+        "number": 8801,
+        "precision": 0.8031156778256546,
+        "recall": 0.8259288717191229
+      },
+      "eval_QTY": {
+        "f1": 0.9873542222846705,
+        "number": 7088,
+        "precision": 0.9833473271760426,
+        "recall": 0.9913939051918735
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7547169811320755,
+        "number": 91,
+        "precision": 0.6611570247933884,
+        "recall": 0.8791208791208791
+      },
+      "eval_UNIT": {
+        "f1": 0.9538566320449514,
+        "number": 5697,
+        "precision": 0.9261034881798644,
+        "recall": 0.9833245567842724
+      },
+      "eval_loss": 0.873456597328186,
+      "eval_overall_accuracy": 0.8422640204422756,
+      "eval_overall_f1": 0.866705292934801,
+      "eval_overall_precision": 0.8401057152296003,
+      "eval_overall_recall": 0.8950443474588202,
+      "eval_runtime": 10.9665,
+      "eval_samples_per_second": 775.635,
+      "eval_steps_per_second": 24.256,
+      "step": 15000
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.9313007325282124e-05,
+      "loss": 0.8414,
+      "step": 15500
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 1.8323104335775097e-05,
+      "loss": 0.845,
+      "step": 16000
+    },
+    {
+      "epoch": 3.17,
+      "eval_COMMENT": {
+        "f1": 0.7413599325653274,
+        "number": 6735,
+        "precision": 0.7035061991734436,
+        "recall": 0.7835189309576838
+      },
+      "eval_NAME": {
+        "f1": 0.8080446927374302,
+        "number": 8801,
+        "precision": 0.7948126167710737,
+        "recall": 0.8217248039995455
+      },
+      "eval_QTY": {
+        "f1": 0.9871533871533871,
+        "number": 7088,
+        "precision": 0.982394858180802,
+        "recall": 0.9919582392776524
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7777777777777778,
+        "number": 91,
+        "precision": 0.719626168224299,
+        "recall": 0.8461538461538461
+      },
+      "eval_UNIT": {
+        "f1": 0.9531036834924966,
+        "number": 5697,
+        "precision": 0.9267119880616813,
+        "recall": 0.981042654028436
+      },
+      "eval_loss": 0.878207266330719,
+      "eval_overall_accuracy": 0.8396895233337817,
+      "eval_overall_f1": 0.8645960176308162,
+      "eval_overall_precision": 0.8431510286001004,
+      "eval_overall_recall": 0.8871603547796706,
+      "eval_runtime": 11.5191,
+      "eval_samples_per_second": 738.424,
+      "eval_steps_per_second": 23.092,
+      "step": 16000
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.7333201346268066e-05,
+      "loss": 0.8353,
+      "step": 16500
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 1.634329835676104e-05,
+      "loss": 0.846,
+      "step": 17000
+    },
+    {
+      "epoch": 3.37,
+      "eval_COMMENT": {
+        "f1": 0.7456715182451542,
+        "number": 6735,
+        "precision": 0.6963411491883535,
+        "recall": 0.8025241276911655
+      },
+      "eval_NAME": {
+        "f1": 0.8116995693753145,
+        "number": 8801,
+        "precision": 0.7992290748898678,
+        "recall": 0.8245653902965572
+      },
+      "eval_QTY": {
+        "f1": 0.9874859392575928,
+        "number": 7088,
+        "precision": 0.984164798206278,
+        "recall": 0.9908295711060948
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7641509433962264,
+        "number": 91,
+        "precision": 0.6694214876033058,
+        "recall": 0.8901098901098901
+      },
+      "eval_UNIT": {
+        "f1": 0.9531343029684443,
+        "number": 5697,
+        "precision": 0.9245874587458746,
+        "recall": 0.9835000877654906
+      },
+      "eval_loss": 0.8758910298347473,
+      "eval_overall_accuracy": 0.8402659032834444,
+      "eval_overall_f1": 0.8662648751088423,
+      "eval_overall_precision": 0.8411751052753739,
+      "eval_overall_recall": 0.8928973673095875,
+      "eval_runtime": 12.1757,
+      "eval_samples_per_second": 698.602,
+      "eval_steps_per_second": 21.847,
+      "step": 17000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.535339536725401e-05,
+      "loss": 0.8452,
+      "step": 17500
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.4363492377746981e-05,
+      "loss": 0.8392,
+      "step": 18000
+    },
+    {
+      "epoch": 3.56,
+      "eval_COMMENT": {
+        "f1": 0.7475519133273144,
+        "number": 6735,
+        "precision": 0.7022442588726514,
+        "recall": 0.799109131403118
+      },
+      "eval_NAME": {
+        "f1": 0.8129017832187377,
+        "number": 8801,
+        "precision": 0.8000660211267606,
+        "recall": 0.8261561186228837
+      },
+      "eval_QTY": {
+        "f1": 0.987295570997403,
+        "number": 7088,
+        "precision": 0.9823997765050985,
+        "recall": 0.9922404063205418
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7809523809523808,
+        "number": 91,
+        "precision": 0.6890756302521008,
+        "recall": 0.9010989010989011
+      },
+      "eval_UNIT": {
+        "f1": 0.9535298615240847,
+        "number": 5697,
+        "precision": 0.9239380968060587,
+        "recall": 0.9850798665964543
+      },
+      "eval_loss": 0.8759370446205139,
+      "eval_overall_accuracy": 0.8409191338930623,
+      "eval_overall_f1": 0.8674550550276846,
+      "eval_overall_precision": 0.8430773319160244,
+      "eval_overall_recall": 0.8932845276643672,
+      "eval_runtime": 12.9734,
+      "eval_samples_per_second": 655.647,
+      "eval_steps_per_second": 20.503,
+      "step": 18000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.3373589388239954e-05,
+      "loss": 0.8436,
+      "step": 18500
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 1.2383686398732925e-05,
+      "loss": 0.8375,
+      "step": 19000
+    },
+    {
+      "epoch": 3.76,
+      "eval_COMMENT": {
+        "f1": 0.7500341670083366,
+        "number": 6735,
+        "precision": 0.6947714900620332,
+        "recall": 0.8148478099480326
+      },
+      "eval_NAME": {
+        "f1": 0.8153302283822457,
+        "number": 8801,
+        "precision": 0.8054323725055432,
+        "recall": 0.8254743779116009
+      },
+      "eval_QTY": {
+        "f1": 0.9877046300850137,
+        "number": 7088,
+        "precision": 0.9837648705388383,
+        "recall": 0.991676072234763
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7751196172248803,
+        "number": 91,
+        "precision": 0.6864406779661016,
+        "recall": 0.8901098901098901
+      },
+      "eval_UNIT": {
+        "f1": 0.9524700280588385,
+        "number": 5697,
+        "precision": 0.9236477572559367,
+        "recall": 0.9831490258030542
+      },
+      "eval_loss": 0.8779729008674622,
+      "eval_overall_accuracy": 0.8412841745278488,
+      "eval_overall_f1": 0.8682191687408367,
+      "eval_overall_precision": 0.8418964491172386,
+      "eval_overall_recall": 0.8962410249190483,
+      "eval_runtime": 12.8106,
+      "eval_samples_per_second": 663.98,
+      "eval_steps_per_second": 20.764,
+      "step": 19000
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 1.1393783409225896e-05,
+      "loss": 0.8358,
+      "step": 19500
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 1.0403880419718868e-05,
+      "loss": 0.8366,
+      "step": 20000
+    },
+    {
+      "epoch": 3.96,
+      "eval_COMMENT": {
+        "f1": 0.7509641873278236,
+        "number": 6735,
+        "precision": 0.7003211303789338,
+        "recall": 0.8095025983667409
+      },
+      "eval_NAME": {
+        "f1": 0.8146694330735154,
+        "number": 8801,
+        "precision": 0.804251550044287,
+        "recall": 0.8253607544597205
+      },
+      "eval_QTY": {
+        "f1": 0.9872137136433891,
+        "number": 7088,
+        "precision": 0.9832073887489504,
+        "recall": 0.9912528216704289
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7783251231527095,
+        "number": 91,
+        "precision": 0.7053571428571429,
+        "recall": 0.8681318681318682
+      },
+      "eval_UNIT": {
+        "f1": 0.9528422125924038,
+        "number": 5697,
+        "precision": 0.9234189723320159,
+        "recall": 0.9842022116903634
+      },
+      "eval_loss": 0.8742325305938721,
+      "eval_overall_accuracy": 0.841668427827624,
+      "eval_overall_f1": 0.8684574531668914,
+      "eval_overall_precision": 0.8434670116429496,
+      "eval_overall_recall": 0.8949739546670421,
+      "eval_runtime": 12.4853,
+      "eval_samples_per_second": 681.281,
+      "eval_steps_per_second": 21.305,
+      "step": 20000
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 9.41397743021184e-06,
+      "loss": 0.8274,
+      "step": 20500
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 8.424074440704812e-06,
+      "loss": 0.8189,
+      "step": 21000
+    },
+    {
+      "epoch": 4.16,
+      "eval_COMMENT": {
+        "f1": 0.7531697905181918,
+        "number": 6735,
+        "precision": 0.7027131284557027,
+        "recall": 0.8114328136599851
+      },
+      "eval_NAME": {
+        "f1": 0.8157082748948107,
+        "number": 8801,
+        "precision": 0.8056294326241135,
+        "recall": 0.8260424951710033
+      },
+      "eval_QTY": {
+        "f1": 0.9872937872937874,
+        "number": 7088,
+        "precision": 0.9825345815285734,
+        "recall": 0.9920993227990971
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7751196172248803,
+        "number": 91,
+        "precision": 0.6864406779661016,
+        "recall": 0.8901098901098901
+      },
+      "eval_UNIT": {
+        "f1": 0.9539115646258504,
+        "number": 5697,
+        "precision": 0.9251195777667821,
+        "recall": 0.9845532736527998
+      },
+      "eval_loss": 0.8799063563346863,
+      "eval_overall_accuracy": 0.8425137850871295,
+      "eval_overall_f1": 0.8695667025328346,
+      "eval_overall_precision": 0.8446531072696506,
+      "eval_overall_recall": 0.8959946501478249,
+      "eval_runtime": 14.411,
+      "eval_samples_per_second": 590.242,
+      "eval_steps_per_second": 18.458,
+      "step": 21000
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 7.434171451197783e-06,
+      "loss": 0.8352,
+      "step": 21500
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 6.444268461690754e-06,
+      "loss": 0.8269,
+      "step": 22000
+    },
+    {
+      "epoch": 4.36,
+      "eval_COMMENT": {
+        "f1": 0.7478056534660309,
+        "number": 6735,
+        "precision": 0.6995086630462891,
+        "recall": 0.8032665181885672
+      },
+      "eval_NAME": {
+        "f1": 0.8122026308424294,
+        "number": 8801,
+        "precision": 0.8004192409532216,
+        "recall": 0.8243381433927963
+      },
+      "eval_QTY": {
+        "f1": 0.987140749068934,
+        "number": 7088,
+        "precision": 0.9833403331933361,
+        "recall": 0.9909706546275395
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7843137254901961,
+        "number": 91,
+        "precision": 0.7079646017699115,
+        "recall": 0.8791208791208791
+      },
+      "eval_UNIT": {
+        "f1": 0.9531422740028915,
+        "number": 5697,
+        "precision": 0.9244473771032663,
+        "recall": 0.9836756187467088
+      },
+      "eval_loss": 0.87808758020401,
+      "eval_overall_accuracy": 0.8418029164825453,
+      "eval_overall_f1": 0.8670379989065063,
+      "eval_overall_precision": 0.8425089653340417,
+      "eval_overall_recall": 0.8930381528931437,
+      "eval_runtime": 13.8025,
+      "eval_samples_per_second": 616.264,
+      "eval_steps_per_second": 19.272,
+      "step": 22000
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 5.4543654721837265e-06,
+      "loss": 0.8231,
+      "step": 22500
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 4.4644624826766974e-06,
+      "loss": 0.829,
+      "step": 23000
+    },
+    {
+      "epoch": 4.55,
+      "eval_COMMENT": {
+        "f1": 0.7491170971539367,
+        "number": 6735,
+        "precision": 0.70192058136517,
+        "recall": 0.8031180400890868
+      },
+      "eval_NAME": {
+        "f1": 0.8114726601811473,
+        "number": 8801,
+        "precision": 0.7987892129884425,
+        "recall": 0.8245653902965572
+      },
+      "eval_QTY": {
+        "f1": 0.9874929735806632,
+        "number": 7088,
+        "precision": 0.9836226203807391,
+        "recall": 0.9913939051918735
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7745098039215685,
+        "number": 91,
+        "precision": 0.6991150442477876,
+        "recall": 0.8681318681318682
+      },
+      "eval_UNIT": {
+        "f1": 0.9533855052739026,
+        "number": 5697,
+        "precision": 0.9249050998514606,
+        "recall": 0.9836756187467088
+      },
+      "eval_loss": 0.8793897032737732,
+      "eval_overall_accuracy": 0.8421679571173317,
+      "eval_overall_f1": 0.8672738768605068,
+      "eval_overall_precision": 0.8428604643438403,
+      "eval_overall_recall": 0.8931437420808109,
+      "eval_runtime": 11.6472,
+      "eval_samples_per_second": 730.305,
+      "eval_steps_per_second": 22.838,
+      "step": 23000
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 3.4745594931696697e-06,
+      "loss": 0.8202,
+      "step": 23500
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.484656503662641e-06,
+      "loss": 0.8183,
+      "step": 24000
+    },
+    {
+      "epoch": 4.75,
+      "eval_COMMENT": {
+        "f1": 0.7519550006859651,
+        "number": 6735,
+        "precision": 0.6988397296952696,
+        "recall": 0.8138084632516703
+      },
+      "eval_NAME": {
+        "f1": 0.8162898973467212,
+        "number": 8801,
+        "precision": 0.806115665854199,
+        "recall": 0.826724235882286
+      },
+      "eval_QTY": {
+        "f1": 0.9871389415981446,
+        "number": 7088,
+        "precision": 0.9834757036829576,
+        "recall": 0.9908295711060948
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7692307692307692,
+        "number": 91,
+        "precision": 0.6837606837606838,
+        "recall": 0.8791208791208791
+      },
+      "eval_UNIT": {
+        "f1": 0.9531422740028915,
+        "number": 5697,
+        "precision": 0.9244473771032663,
+        "recall": 0.9836756187467088
+      },
+      "eval_loss": 0.8815182447433472,
+      "eval_overall_accuracy": 0.8428019750619609,
+      "eval_overall_f1": 0.8690636678554975,
+      "eval_overall_precision": 0.8434860379608466,
+      "eval_overall_recall": 0.8962410249190483,
+      "eval_runtime": 10.2447,
+      "eval_samples_per_second": 830.287,
+      "eval_steps_per_second": 25.965,
+      "step": 24000
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 1.4947535141556129e-06,
+      "loss": 0.8271,
+      "step": 24500
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 5.048505246485845e-07,
+      "loss": 0.8201,
+      "step": 25000
+    },
+    {
+      "epoch": 4.95,
+      "eval_COMMENT": {
+        "f1": 0.7506890848952591,
+        "number": 6735,
+        "precision": 0.7003986112897004,
+        "recall": 0.8087602078693392
+      },
+      "eval_NAME": {
+        "f1": 0.8135612216307089,
+        "number": 8801,
+        "precision": 0.8026315789473685,
+        "recall": 0.8247926372003181
+      },
+      "eval_QTY": {
+        "f1": 0.9874235930583853,
+        "number": 7088,
+        "precision": 0.9834849545136459,
+        "recall": 0.9913939051918735
+      },
+      "eval_RANGE_END": {
+        "f1": 0.7788461538461537,
+        "number": 91,
+        "precision": 0.6923076923076923,
+        "recall": 0.8901098901098901
+      },
+      "eval_UNIT": {
+        "f1": 0.9532153793807416,
+        "number": 5697,
+        "precision": 0.9247400561148704,
+        "recall": 0.9835000877654906
+      },
+      "eval_loss": 0.8807578682899475,
+      "eval_overall_accuracy": 0.8429172510518934,
+      "eval_overall_f1": 0.8681558902893056,
+      "eval_overall_precision": 0.8432419879238272,
+      "eval_overall_recall": 0.8945867943122624,
+      "eval_runtime": 10.211,
+      "eval_samples_per_second": 833.024,
+      "eval_steps_per_second": 26.05,
+      "step": 25000
+    },
+    {
+      "epoch": 5.0,
+      "step": 25255,
+      "total_flos": 3120524263271436.0,
+      "train_loss": 0.8656694423182368,
+      "train_runtime": 2424.3674,
+      "train_samples_per_second": 333.289,
+      "train_steps_per_second": 10.417
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 25255,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "total_flos": 3120524263271436.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3cd944052e431388bcf84fd583eb6e10945630d9735c7c812639db2f4d8557
+size 4091

validation_results.json

@@ -0,0 +1,41 @@
+{
+    "epoch": 5.0,
+    "eval_COMMENT": {
+        "f1": 0.7449105068998496,
+        "number": 6735,
+        "precision": 0.6898646083765658,
+        "recall": 0.8095025983667409
+    },
+    "eval_NAME": {
+        "f1": 0.8143625364104862,
+        "number": 8801,
+        "precision": 0.8031156778256546,
+        "recall": 0.8259288717191229
+    },
+    "eval_QTY": {
+        "f1": 0.9873542222846705,
+        "number": 7088,
+        "precision": 0.9833473271760426,
+        "recall": 0.9913939051918735
+    },
+    "eval_RANGE_END": {
+        "f1": 0.7547169811320755,
+        "number": 91,
+        "precision": 0.6611570247933884,
+        "recall": 0.8791208791208791
+    },
+    "eval_UNIT": {
+        "f1": 0.9538566320449514,
+        "number": 5697,
+        "precision": 0.9261034881798644,
+        "recall": 0.9833245567842724
+    },
+    "eval_loss": 0.873456597328186,
+    "eval_overall_accuracy": 0.8422640204422756,
+    "eval_overall_f1": 0.866705292934801,
+    "eval_overall_precision": 0.8401057152296003,
+    "eval_overall_recall": 0.8950443474588202,
+    "eval_runtime": 12.6045,
+    "eval_samples_per_second": 674.839,
+    "eval_steps_per_second": 21.104
+}